© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38270
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     использоваться
    0.52
     ("
    0.50
     (
    0.50
     VOC
    0.48
     используется
    0.47
     ('
    0.47
     USE
    0.46
    uden
    0.45
     तौर
    0.45
    े
    0.44
    POSITIVE LOGITS
    لي
    0.52
     Ezekiel
    0.52
    opholes
    0.52
     Shaikh
    0.48
    SuspendLayout
    0.48
     Sion
    0.46
    深入
    0.46
    Citizen
    0.46
    gateTime
    0.45
     ਵਾਲ
    0.45
    Activations Density 0.000%

    No Known Activations